def format_credible_intervals(event_name, samples, confidence_level=0.95):
"""
Returns a list of print-able credible intervals for an NxM samples
matrix. Handles both the two isoform and multi-isoform cases.
"""
num_samples, num_isoforms = shape(samples)
if num_isoforms > 2:
cred_interval = ht.compute_multi_iso_credible_intervals(
samples, confidence_level=confidence_level)
cred_interval_lowbounds = ",".join(
[str("%.2f" % (ci[0])) for ci in cred_interval])
cred_interval_highbounds = ",".join(
[str("%.2f" % (ci[1])) for ci in cred_interval])
posterior_mean = ",".join("%.2f" % (val) for val in mean(samples, 0))
output_fields = [
event_name,
"%s" % (posterior_mean),
"%s" % (cred_interval_lowbounds),
"%s" % (cred_interval_highbounds)
]
else:
cred_interval = ht.compute_credible_intervals(samples)
posterior_mean = mean(samples, 0)[0]
output_fields = [
event_name,
"%.2f" % (posterior_mean),
"%.2f" % (cred_interval[0]),
"%.2f" % (cred_interval[1])
]
return output_fields
def format_credible_intervals(event_name, samples,
confidence_level=0.95):
"""
Returns a list of print-able credible intervals for an NxM samples
matrix. Handles both the two isoform and multi-isoform cases.
"""
num_samples, num_isoforms = shape(samples)
if num_isoforms > 2:
cred_interval = ht.compute_multi_iso_credible_intervals(samples,
confidence_level=confidence_level)
cred_interval_lowbounds = ",".join([str("%.2f" %(ci[0])) for ci in cred_interval])
cred_interval_highbounds = ",".join([str("%.2f" %(ci[1])) for ci in cred_interval])
posterior_mean = ",".join("%.2f" %(val) for val in mean(samples, 0))
output_fields = [event_name,
"%s" %(posterior_mean),
"%s" %(cred_interval_lowbounds),
"%s" %(cred_interval_highbounds)]
else:
cred_interval = ht.compute_credible_intervals(samples)
posterior_mean = mean(samples, 0)[0]
output_fields = [event_name,
"%.2f" %(posterior_mean),
"%.2f" %(cred_interval[0]),
"%.2f" %(cred_interval[1])]
return output_fields
def plot_two_iso_samples(self,
fig=None,
isoform_index=0,
num_rows=1,
num_cols=1,
subplot_start=1,
plots_dir=None,
map_estimate=None,
simulation_num=1,
plot_intervals=False,
value_to_label=None,
label=None,
plot_filename=None,
bins=None,
bbox_coords=None,
with_legend=True,
title=None,
vanilla=False,
plot_mean=False,
normed=False,
fig_dims=(5, 5)):
"""
Plot a set of samples for Psi of a two isoform gene.
"""
if not fig:
sampled_psi_fig = plt.figure(figsize=fig_dims, dpi=300)
else:
sampled_psi_fig = fig
ax = sampled_psi_fig.add_subplot(num_rows, num_cols, subplot_start)
num_iters = int(self.params['iters'])
burn_in = int(self.params['burn_in'])
lag = int(self.params['lag'])
percent_acceptance = float(self.params['percent_accept'])
proposal_type = self.params['proposal_type']
plt.rcParams['font.size'] = 10
show_spines(ax, ['left', 'bottom'])
bins = bins
assert((value_to_label == None and label == None) or \
(value_to_label != None and label != None))
# retrieve samples
samples_to_plot = self.samples[:, isoform_index]
# picasso blue #0276FD
if not vanilla:
if bins != None:
plt.hist(samples_to_plot,
align='center',
lw=0.5,
facecolor='#0276FD',
edgecolor='#ffffff')
else:
plt.hist(samples_to_plot,
align='center',
lw=0.5,
facecolor='#0276FD',
edgecolor='#ffffff')
else:
plt.hist(samples_to_plot,
align='center',
facecolor='#0276FD',
edgecolor='#0276FD')
plt.xlabel(r'${\hat{\Psi}}_{\mathregular{MISO}}$')
plt.ylabel('Frequency')
plt.xlim([0, 1])
# Normalize samples
if normed:
yticks = list(plt.gca().get_yticks())
print "yticks: ", yticks
ytick_labels = [
"%.2f" % (float(ytick) / float(normed)) for ytick in yticks
]
ax.set_yticklabels(ytick_labels)
# samples_to_plot = samples_to_plot / float(len(samples_to_plot))
# curr_tick_labels = [label.get_label() for label in ax.get_yticklabels()]
# print "Current tick labels: ", curr_tick_labels
# new_tick_labels = []
# for label in curr_tick_labels:
# if len(label) > 0:
# new_label = "%.1f" %(float(label) / normed)
# else:
# new_label = ""
# new_tick_labels.append(new_label)
# #ax.set_yticklabels(new_tick_labels)
curr_axes = plt.gca()
# Plot MAP estimate for same data
if map_estimate:
l = plt.axvline(x=map_estimate,
color='b',
linewidth=1.2,
ls='-',
label=r'${\hat{\Psi}}_{MAP}\ =\ %.2f$' %
(map_estimate))
# Plot true Psi
if self.true_psi:
plot_id = "%dsimul_%diters_%dburnin_%dlag_%s_truepsi_%.2f.pdf" % (
simulation_num, num_iters, burn_in, lag, proposal_type,
self.true_psi)
l = plt.axvline(x=self.true_psi,
color='r',
linewidth=1.2,
ls='-',
label=r'True $\Psi$')
else:
# Unknown true Psi
plot_id = "%dsimul_%diters_%dburnin_%dlag_%s_%s_truepsi.pdf" % (
simulation_num, num_iters, burn_in, lag, proposal_type,
'unknown')
if value_to_label:
l = plt.axvline(x=value_to_label,
color='r',
linewidth=1.2,
ls='-',
label=label)
# plot credible intervals if given
if plot_intervals:
# print "Plotting %.2f confidence intervals" %(plot_intervals * 100)
interval_c1, interval_c2 = ht.compute_credible_intervals(
samples_to_plot, plot_intervals)
plt.axvline(x=interval_c1,
color='#999999',
linewidth=0.7,
ls='--',
label=r'%d' % (plot_intervals * 100) + '% CI')
plt.axvline(x=interval_c2, color='#999999', linewidth=0.7, ls='--')
if plot_mean:
sample_mean = mean(samples_to_plot)
plt.axvline(x=sample_mean, color='r', linewidth=0.8, label='Mean')
if with_legend and (plot_intervals or self.true_psi):
if not bbox_coords:
lg = plt.legend(handletextpad=0.172,
borderpad=0.01,
labelspacing=.008,
handlelength=1.4,
loc='best',
numpoints=1)
else:
lg = plt.legend(handletextpad=0.172,
borderpad=0.01,
labelspacing=.008,
handlelength=1.4,
loc='best',
numpoints=1,
bbox_to_anchor=bbox_coords)
lg.get_frame().set_linewidth(0)
for t in lg.get_texts():
t.set_fontsize(8)
if title:
plt.title(title)
if plots_dir:
if not plot_filename:
plt.savefig(plots_dir + "sampled_psi_hist_%s" % (plot_id))
else:
plt.savefig(plots_dir + plot_filename + '.pdf')
return curr_axes
def plot_two_iso_samples(self, fig=None, isoform_index=0, num_rows=1, num_cols=1, subplot_start=1,
plots_dir=None, map_estimate=None, simulation_num=1,
plot_intervals=False, value_to_label=None, label=None, plot_filename=None,
bins=None, bbox_coords=None, with_legend=True, title=None, vanilla=False,
plot_mean=False, normed=False):
"""
Plot a set of samples for Psi of a two isoform gene.
"""
if not fig:
sampled_psi_fig = plt.figure(figsize=(2.5, 2.2), dpi=300)
else:
sampled_psi_fig = fig
ax = sampled_psi_fig.add_subplot(num_rows, num_cols, subplot_start)
num_iters = int(self.params['iters'])
burn_in = int(self.params['burn_in'])
lag = int(self.params['lag'])
percent_acceptance = float(self.params['percent_accept'])
proposal_type = self.params['proposal_type']
plt.rcParams['font.size'] = 10
# show_spines(ax, ['left', 'bottom'])
bins = bins
assert((value_to_label == None and label == None) or \
(value_to_label != None and label != None))
# retrieve samples
samples_to_plot = self.samples[:, isoform_index]
# picasso blue #0276FD
print "normed: ", normed, " bins: ", bins
if not vanilla:
if bins != None:
plt.hist(samples_to_plot, align='center', lw=0.5, facecolor='#0276FD',
edgecolor='#ffffff')
else:
plt.hist(samples_to_plot, align='center', lw=0.5, facecolor='#0276FD',
edgecolor='#ffffff')
else:
plt.hist(samples_to_plot, align='center', facecolor='#0276FD', edgecolor='#0276FD')
plt.xlabel(r'${\hat{\Psi}}_{\mathregular{MISO}}$')
plt.ylabel('Frequency')
plt.xlim([0, 1])
# Normalize samples
if normed:
yticks = list(plt.gca().get_yticks())
print "yticks: ", yticks
ytick_labels = ["%.2f" %(float(ytick) / float(normed)) for ytick in yticks]
ax.set_yticklabels(ytick_labels)
# samples_to_plot = samples_to_plot / float(len(samples_to_plot))
# curr_tick_labels = [label.get_label() for label in ax.get_yticklabels()]
# print "Current tick labels: ", curr_tick_labels
# new_tick_labels = []
# for label in curr_tick_labels:
# if len(label) > 0:
# new_label = "%.1f" %(float(label) / normed)
# else:
# new_label = ""
# new_tick_labels.append(new_label)
# #ax.set_yticklabels(new_tick_labels)
curr_axes = plt.gca()
# Plot MAP estimate for same data
if map_estimate:
l = plt.axvline(x=map_estimate, color='b', linewidth=1.2, ls='-', label=r'${\hat{\Psi}}_{MAP}\ =\ %.2f$' %(map_estimate))
# Plot true Psi
if self.true_psi:
plot_id = "%dsimul_%diters_%dburnin_%dlag_%s_truepsi_%.2f.pdf" %(simulation_num, num_iters, burn_in, lag, proposal_type, self.true_psi)
l = plt.axvline(x=self.true_psi, color='r', linewidth=1.2, ls='-', label=r'True $\Psi$')
else:
# Unknown true Psi
plot_id = "%dsimul_%diters_%dburnin_%dlag_%s_%s_truepsi.pdf" %(simulation_num, num_iters, burn_in, lag, proposal_type, 'unknown')
if value_to_label:
l = plt.axvline(x=value_to_label, color='r', linewidth=1.2, ls='-', label=label)
# plot credible intervals if given
if plot_intervals:
# print "Plotting %.2f confidence intervals" %(plot_intervals * 100)
interval_c1, interval_c2 = ht.compute_credible_intervals(samples_to_plot, plot_intervals)
plt.axvline(x=interval_c1, color='#999999', linewidth=0.7, ls='--',
label=r'%d' %(plot_intervals*100) + '% CI')
plt.axvline(x=interval_c2, color='#999999', linewidth=0.7, ls='--')
if plot_mean:
sample_mean = mean(samples_to_plot)
plt.axvline(x=sample_mean, color='r', linewidth=0.8, label='Mean')
if with_legend and (plot_intervals or self.true_psi):
if not bbox_coords:
lg = plt.legend(handletextpad=0.172, borderpad=0.01, labelspacing=.008, handlelength=1.4, loc='best', numpoints=1)
else:
lg = plt.legend(handletextpad=0.172, borderpad=0.01, labelspacing=.008, handlelength=1.4, loc='best', numpoints=1,
bbox_to_anchor=bbox_coords)
lg.get_frame().set_linewidth(0)
for t in lg.get_texts():
t.set_fontsize(8)
if title:
plt.title(title)
if plots_dir:
if not plot_filename:
plt.savefig(plots_dir + "sampled_psi_hist_%s" %(plot_id))
else:
plt.savefig(plots_dir + plot_filename + '.pdf')
return curr_axes
